28 accepted papers
Diffusion transformers have demonstrated remarkable generation quality, albeit requiring longer training iterations and numerous inference steps. In each denoising step, diffusion transformers encode the noisy inputs to extract the lower-frequency semantic component and then decode the higher freque
While Reinforcement Learning from Human Feedback (RLHF) has become a pivotal paradigm for text-to-image generation, its application to image editing remains largely unexplored. A key bottleneck is the lack of a robust general reward model for all editing tasks. Existing edit reward models usually gi
The current success of diffusion transformers are built on the compressed latent space shaped by the pre-trained variational autoencoder(VAE). However, this two-stage training paradigm inevitably introduces accumulated errors and decoding artifacts. To avoid these problems, researchers return to pix…
Autoregressive (AR) models have demonstrated strong potential in visual generation, offering competitive performance with simple architectures and optimization objectives. However, existing methods are typically limited to single-modality conditions, \eg, text or category labels, restricting their a…
Text-to-video models have made remarkable advancements through optimization on high-quality text-video pairs, where the textual prompts play a pivotal role in determining quality of output videos. However, achieving the desired output often entails multiple revisions and iterative inference to refin…
Diffusion Transformers have emerged as the foundation for vision generative models, but their scalability is limited by the high cost of hyperparameter (HP) tuning at large scales. Recently, Maximal Update Parametrization ($\mu$P) was proposed for vanilla Transformers, which enables stable HP transf…
This paper presents a computational model for universal video temporal grounding, which accurately localizes temporal moments in videos based on natural language queries (e.g., questions or descriptions). Unlike existing methods that are often limited to specific video domains or durations, we prop…
"Vision-Language Large Models (VLMs) recently become primary backbone of AI, due to the impressive performance. However, their expensive computation costs, i.e., throughput and delay, impede potentials in the real-world scenarios. To achieve acceleration for VLMs, most existing methods focus on the…
Latent diffusion models (LDM) have revolutionized text-to-image generation, leading to the proliferation of various advanced models and diverse downstream applications. However, despite these significant advancements, current diffusion models still suffer from several limitations, including inferior…
In this paper, we present a new cross-architecture contrastive learning (CACL) framework for self-supervised video representation learning. CACL consists of a 3D CNN and a video transformer which are used in parallel to generate diverse positive pairs for contrastive learning. This allows the model…
This work aims at improving instance retrieval with self-supervision. We find that fine-tuning using the recently developed self-supervised learning (SSL) methods, such as SimCLR and MoCo, fails to improve the performance of instance retrieval. In this work, we identify that the learnt representatio…
Recent advances in neuroscience have highlighted the effectiveness of multi-modal medical data for investigating certain pathologies and understanding human cognition. However, obtaining full sets of different modalities is limited by various factors, such as long acquisition times, high examination…
The conventional detectors tend to make imbalanced classification and suffer performance drop, when the distribution of the training data is severely skewed. In this paper, we propose to use the mean classification score to indicate the classification accuracy for each category during training. Base…
One-stage object detection is commonly implemented by optimizing two sub-tasks: object classification and localization, using heads with two parallel branches, which might lead to a certain level of spatial misalignment in predictions between the two tasks. In this work, we propose a Task-aligned On…
Differentiable architecture search (DAS) has made great progress in searching for high-performance architectures with reduced computational cost. However, DAS-based methods mainly focus on searching for a repeatable cell structure, which is then stacked sequentially in multiple stages to form the n…
Mining informative negative instances are of central importance to deep metric learning (DML). However, the hard-mining ability of existing DML methods is intrinsically limited by mini-batch training, where only a mini-batch of instances are accessible at each iteration. In this paper, we identify a…
Siamese-based trackers have achieved excellent performance on visual object tracking. However, the target template is not updated online, and the features of target template and search image are computed independently in a Siamese architecture. In this paper, we propose Deformable Siamese Attention…
Region Proposal Network (RPN) provides strong support for handling the scale variation of objects in two-stage object detection. For one-stage detectors which do not have RPN, it is more demanding to have powerful sub-networks capable of directly capturing objects of unknown sizes. To enhance such c…
Most existing 3D CNN structures for video representation learning are clip-based methods, and do not consider video-level temporal evolution of spatio-temporal features. In this paper, we propose Video-level 4D Convolutional Neural Networks, namely V4D, to model the evolution of long-range spatio-te…
We present ClothFlow, an appearance-flow-based generative model to synthesize clothed person for posed-guided person image generation and virtual try-on. By estimating a dense flow between source and target clothing regions, ClothFlow effectively models the geometric changes and naturally transfers…
Recent progress has been made on developing a unified framework for joint text detection and recognition in natural images, but existing joint models were mostly built on two-stage framework by involving ROI pooling, which can degrade the performance on recognition task. In this work, we propose con…
Multi-label image classification has achieved remarkable progress thanks to deep convolutional neural networks (CNNs). In this paper, we propose a Decouple Network (DecoupleNet) which is an end-to-end CNN-based framework able to trade off class-level feature independence and relevance during trainin…
Visual compatibility is critical for fashion analysis, yet is missing in existing fashion image synthesis systems. In this paper, we propose to explicitly model visual compatibility through fashion image inpainting. We present Fashion Inpainting Networks (FiNet), a two-stage image-to-image generatio…
Weakly-supervised instance segmentation aims to detect and segment object instances precisely, given image-level labels only. Unlike previous methods which are composed of multiple offline stages, we propose Sequential Label Propagation and Enhancement Networks (referred as Label-PEnet) that progres…
A family of loss functions built on pair-based computation have been proposed in the literature which provide a myriad of solutions for deep metric learning. In this pa-per, we provide a general weighting framework for under-standing recent pair-based loss functions. Our contributions are t…
Text detection and recognition in natural images have long been considered as two separate tasks that are processed sequentially. Jointly training two tasks is non-trivial due to significant differences in learning difficulties and convergence rates. In this work, we present a conceptually simple ye…
We present a simple yet efficient approach capable of training deep neural networks on large-scale weakly-supervised web images, which are crawled rawly from the Internet by using text queries, without any human annotation. We develop a principled learning strategy by leveraging curriculum learning,…
We present a novel single-shot text detector that directly outputs word-level bounding boxes in a natural image. We propose an attention mechanism which roughly identifies text regions via an automatically learned attentional map. This substantially suppresses background interference in the convolut…