38 accepted papers
CLIP is a seminal multimodal model that maps images and text into a shared representation space by contrastive learning on billions of image–caption pairs. Inspired by the rapid progress of large language models (LLMs), we investigate how the superior linguistic understanding and broad world knowled
In this paper, we empirically demonstrate that natural images can be reconstructed with high fidelity from compressed representations using a simple first-order norm-plus-linear autoregressive (FINOLA) process—without relying on explicit positional information. Through systematic analysis, we observ…
Video understanding is essential for multimodal large language models (MLLMs) to interact effectively with users and the real world. However, analyzing long videos remains a major challenge due to the lack of high-quality video instruction data and effective training strategies. In this paper, we in
Most large multimodal models (LMMs) are implemented by feeding visual tokens as a sequence into the first layer of a large language model (LLM). The resulting architecture is simple but significantly increases computation and memory costs, as it has to handle a large number of additional tokens in…
In this work, we present efficient modulation, a novel design for efficient vision networks. We revisit the modulation mechanism, which operates input through convolutional context modeling and feature projection layers, and fuses features via element-wise multiplication and an MLP block. We demonst…
We introduce Florence-2 a novel vision foundation model with a unified prompt-based representation for various computer vision and vision-language tasks. While existing large vision models excel in transfer learning they struggle to perform diverse tasks with simple instructions a capability that im…
Recent studies have drawn attention to the untapped potential of the "star operation" (element-wise multiplication) in network design. While intuitive explanations abound the foundational rationale behind its application remains largely unexplored. Our study attempts to reveal the star operation's a…
Combining multiple datasets enables performance boost on many computer vision tasks. But similar trend has not been witnessed in object detection when combining multiple datasets due to two inconsistencies among detection datasets: taxonomy difference and domain gap. In this paper, we address these…
We present X-Decoder, a generalized decoding model that can predict pixel-level segmentation and language tokens seamlessly. X-Decoder takes as input two types of queries: (i) generic non-semantic queries and (ii) semantic queries induced from text inputs, to decode different pixel-level and token-l…
End-to-end Transformers have demonstrated an impressive success rate for Embodied Instruction Following when the environment has been seen in training. However, they tend to struggle when deployed in an unseen environment. This lack of generalizability is due to the agent’s insensitivity to subtle c…
Recently, both Contrastive Learning (CL) and Mask Image Modeling (MIM) demonstrate that self-supervision is powerful to learn good representations. However, naively combining them is far from success. In this paper, we start by making the empirical observation that a naive joint optimization of CL a…
Long-tailed object detection (LTOD) aims to handle the extreme data imbalance in real-world datasets, where many tail classes have scarce instances. One popular strategy is to explore extra data with image-level labels, yet it produces limited results due to (1) semantic ambiguity---an image-level l…
Exploring dense matching between the current frame and past frames for long-range context modeling, memory-based methods have demonstrated impressive results in video object segmentation (VOS) recently. Nevertheless, due to the lack of instance understanding ability, the above approaches are oftenti…
Benefiting from masked visual modeling, self-supervised video representation learning has achieved remarkable progress. However, existing methods focus on learning representations from scratch through reconstructing low-level features like raw pixel values. In this paper, we propose masked video dis…
This paper studies the BERT pretraining of video transformers. It is a straightforward but worth-studying extension given the recent success from BERT pretraining of image transformers. We introduce BEVT which decouples video representation learning into spatial representation learning and temporal…
This paper investigates two techniques for developing efficient self-supervised vision transformers (EsViT) for visual representation learning. First, we show through a comprehensive empirical study that multi-stage architectures with sparse self-attentions can significantly reduce modeling complexi…
We propose focal modulation networks (FocalNets in short), where self-attention (SA) is completely replaced by a focal modulation module for modeling token interactions in vision. Focal modulation comprises three components: $(i)$ hierarchical contextualization, implemented using a stack of depth-wi…
We present GLIPv2, a grounded VL understanding model, that serves both localization tasks (e.g., object detection, instance segmentation) and Vision-Language (VL) understanding tasks (e.g., VQA, image captioning). GLIPv2 elegantly unifies localization pre-training and Vision-Language Pre-training (V…
We present Mobile-Former, a parallel design of MobileNet and transformer with a two-way bridge in between. This structure leverages the advantages of MobileNet at local processing and transformer at global interaction. And the bridge enables bidirectional fusion of local and global features. Differe…
Transformers have achieved great success in pluralistic image inpainting recently. However, we find existing transformer based solutions regard each pixel as a token, thus suffer from information loss issue from two aspects: 1) They downsample the input image into much lower resolutions for efficien…
Contrastive language-image pretraining (CLIP) using image-text pairs has achieved impressive results on image classification in both zero-shot and transfer learning settings. However, we show that directly applying such models to recognize image regions for object detection leads to unsatisfactory p…
"The complexity-precision trade-off of an object detector is a critical problem for resource constrained vision tasks. Previous works have emphasized detectors implemented with efficient backbones. The impact on this trade-off of proposal processing by the detection head is investigated in this work…
People say, "A picture is worth a thousand words". Then how can we get the rich information out of the image? We argue that by using visual clues to bridge large pretrained vision foundation models and language models, we can do so without any extra cross-modal training. Thanks to the strong zero-sh…
We present in this paper a new architecture, named Convolutional vision Transformer (CvT), that improves Vision Transformer (ViT) in performance and efficiency by introducing convolutions into ViT to yield the best of both designs. This is accomplished through two primary modifications: a hierarchy…
In this paper, we present a novel Dynamic DETR (Detection with Transformers) approach by introducing dynamic attentions into both the encoder and decoder stages of DETR to break its two limitations on small feature resolution and slow training convergence. To address the first limitation, which is d…
The complex nature of combining localization and classification in object detection has resulted in the flourished development of methods. Previous works tried to improve the performance in various object detection heads but failed to present a unified view. In this paper, we present a novel dynamic…
Recently, Vision Transformer and its variants have shown great promise on various computer vision tasks. The ability to capture local and global visual dependencies through self-attention is the key to its success. But it also brings challenges due to quadratic computational overhead, especially for…
This paper aims at addressing the problem of substantial performance degradation at extremely low computational cost (e.g. 5M FLOPs on ImageNet classification). We found that two factors, sparse connectivity and dynamic activation function, are effective to improve the accuracy. The former avoids th…
This paper presents a new Vision Transformer (ViT) architecture Multi-Scale Vision Longformer, which significantly enhances the ViT of [??] for encoding high-resolution images using two techniques. The first is the multi-scale model structure, which provides image encodings at multiple scales with…
Recent research in dynamic convolution shows substantial performance boost for efficient CNNs, due to the adaptive aggregation of K static convolution kernels. It has two limitations: (a) it increases the number of convolutional weights by K-times, and (b) the joint optimization of dynamic attention…
Neural Architecture Search (NAS) often trains and evaluates a large number of architectures. Recent predictor-based NAS approaches attempt to alleviate such heavy computation costs with two key steps: sampling some architecture-performance pairs and fitting a proxy accuracy predictor. Given limited…
Efficient search is a core issue in Neural Architecture Search (NAS). It is difficult for conventional NAS algorithms to directly search the architectures on large-scale tasks like ImageNet. In general, the cost of GPU hours for NAS grows with regard to training dataset size and candidate set size.…
Light-weight convolutional neural networks (CNNs) suffer performance degradation as their low computational budgets constrain both the depth (number of convolution layers) and the width (number of channels) of CNNs, resulting in limited representation capability. To address this issue, we present Dy…
Rectified linear units (ReLU) are commonly used in deep neural networks. So far ReLU and its generalizations (non-parametric or parametric) are static, performing identically for all input samples. In this paper, we propose dynamic ReLU (DY-ReLU), a dynamic rectifier of which parameters are generate…
Existing Temporal Activity Localization (TAL) methods largely adopt strong supervision for model training, which requires (1) vast amounts of untrimmed videos per each activity category and (2) accurate segment-level boundary annotations (start time and end time) for every instance. This poses a cri…
This research strives for natural language moment retrieval in long, untrimmed video streams. The problem is not trivial especially when a video contains multiple moments of interests and the language describes complex temporal dependencies, which often happens in real scenarios. We identify two cr…
Deep networks have shown impressive performance on many computer vision tasks. Recently, deep convolutional neural networks (CNNs) have been used to learn discriminative texture representations. One of the most successful approaches is Bilinear CNN model that explicitly captures the second order sta…
We present a Temporal Context Network (TCN) for precise temporal localization of human activities. Similar to the Faster-RCNN architecture, proposals are placed at equal intervals in a video which span multiple temporal scales. We propose a novel representation for ranking these proposals. Since poo…