26 accepted papers
Flow matching models have emerged as a powerful framework for realistic image generation by learning to reverse a corruption process that progressively adds Gaussian noise. However, because noise is injected in the latent domain, its impact on different frequency components is non-uniform. As a resu
Rotary Position Embedding (RoPE) is the de facto positional encoding in large language models due to its ability to encode relative positions and support length extrapolation. When adapted to vision transformers, the standard axial formulation decomposes two-dimensional spatial positions into horizo…
Recent advances in image editing models have demonstrated remarkable capabilities in executing explicit instructions, such as attribute manipulation, style transfer, and pose synthesis. However, these models often face challenges when dealing with implicit editing instructions, which describe the…
Conventional practice assumes that online reinforcement learning for flow-matching models requires sampling full denoising trajectories to compute rewards. This assumption underlies methods such as Group Relative Policy Optimization (GRPO), where the policy must traverse the entire reverse process b…
In this work, we introduce the Adventurer series models where we treat images as sequences of patch tokens and employ uni-directional language models to learn visual representations. This modeling paradigm allows us to process images in a recurrent formulation with linear complexity relative to the…
The vision community has started to build with the recently developed state space model, Mamba, as the new backbone for a range of tasks. This paper shows that Mamba's visual capability can be significantly enhanced through autoregressive pretraining, a direction not previously explored. Efficiency-…
Autoregressive (AR) modeling, known for its next-token prediction paradigm, underpins state-of-the-art language and visual generative models. Traditionally, a "token" is treated as the smallest prediction unit, often a discrete symbol in language or a quantized patch in vision. However, the optimal…
Autoregressive (AR) modeling has achieved remarkable success in natural language processing by enabling models to generate text with coherence and contextual understanding through next token prediction. Recently, in image generation, VAR proposes scale-wise autoregressive modeling, which extends the…
Similar to Vision Transformers, this paper identifies artifacts also present within the feature maps of Vision Mamba. These artifacts, corresponding to high-norm tokens emerging in low-information background areas of images, appear much more severe in Vision Mamba---they exist prevalently even with…
Web-crawled image-text pairs are inherently noisy. Prior studies demonstrate that semantically aligning and enriching textual descriptions of these pairs can significantly enhance model training across various vision-language tasks, particularly text-to-image generation. However, large-scale investi…
This paper enhances image-GPT (iGPT), one of the pioneering works that introduce autoregressive pretraining to predict the next pixels for visual representation learning. Two simple yet essential changes are made. First, we shift the prediction target from raw pixels to semantic tokens, enabling a h…
Vision Transformer has demonstrated impressive success across various vision tasks. However, its heavy computation cost, which grows quadratically with respect to the token sequence length, largely limits its power in handling large feature maps. To alleviate the computation cost, previous works rel…
Inspired by the success of self-supervised autoregressive representation learning in natural language (GPT and its variants), and advances in recent visual architecture design with Vision Transformers (ViTs), in this paper, we explore the effects various design choices have on the success of applyin…
Crossmodal knowledge distillation (KD) extends traditional knowledge distillation to the area of multimodal learning and demonstrates great success in various applications. To achieve knowledge transfer across modalities, a pretrained network from one modality is adopted as the teacher to provide su…
Masked image modeling (MIM) performs strongly in pre-training large vision Transformers (ViTs). However, small models that are critical for real-world applications cannot or only marginally benefit from this pre-training approach. In this paper, we explore distillation techniques to transfer the suc…
Data mixing (e.g., Mixup, Cutmix, ResizeMix) is an essential component for advancing recognition models. In this paper, we focus on studying its effectiveness in the self-supervised setting. By noticing the mixed images that share the same source images are intrinsically related to each other, we he…
The inductive bias of vision transformers is more relaxed that cannot work well with insufficient data. Knowledge distillation is thus introduced to assist the training of transformers. Unlike previous works, where merely heavy convolution-based teachers are provided, in this paper, we delve into th…
"One key challenge of exemplar-guided image generation lies in establishing fine-grained correspondences between input and guided images. Prior approaches, despite the promising results, have relied on either estimating dense attention to compute per-point matching, which is limited to only coarse s…
"Data lies at the core of modern deep learning. The impressive performance of supervised learning is built upon a base of massive accurately labeled data. However, in some real-world applications, accurate labeling might not be viable; instead, multiple noisy labels (instead of one accurate label) a…
Recent Vision Transformer (ViT) models have demonstrated encouraging results across various computer vision tasks, thanks to its competence in modeling long-range dependencies of image patches or tokens via self-attention. These models, however, usually designate the similar receptive fields of each…
This paper tackles the task of Few-Shot Video Object Segmentation (FSVOS), i.e., segmenting objects in the query videos with certain class specified in a few labeled support images. The key is to model the relationship between the query videos and the support images for propagating the object inform…
Lip reading aims to predict the spoken sentences from silent lip videos. Due to the fact that such a vision task usually performs worse than its counterpart speech recognition, one potential scheme is to distill knowledge from a teacher pretrained by audio signals. However, the latent domain gap bet…
The popularity of multimodal sensors and the accessibility of the Internet have brought us a massive amount of unlabeled multimodal data. Since existing datasets and well-trained models are primarily unimodal, the modality gap between a unimodal network and unlabeled multimodal data poses an interes…
In self-supervised representation learning, a common idea behind most of the state-of-the-art approaches is to enforce the robustness of the representations to predefined augmentations. A potential issue of this idea is the existence of completely collapsed solutions (i.e., constant features), which…
Unsupervised video object segmentation (UVOS) aims at segmenting the primary objects in videos without any human intervention. Due to the lack of prior knowledge about the primary objects, identifying them from videos is the major challenge of UVOS. Previous methods often regard the moving objects a…
In this paper, we propose a simple yet effective approach, named Triple Excitation Network, to reinforce the training of video salient object detection (VSOD) from three aspects, spatial, temporal, and online excitations. These excitation mechanisms are designed following the spirit of curriculum le…