14 accepted papers
Direct Preference Optimization (DPO) has become the de facto standard for offline preference alignment of large language models, but its reliance on a reference policy introduces a critical tension. DPO weighs each update relative to a reference, which stabilizes the training by regularizing the up…
Reinforcement Learning from Human Feedback (RLHF) has advanced alignment capabilities significantly but remains hindered by two core challenges: reward hacking and stable optimization. Current solutions independently address these issues through separate regularization strategies, specifically a KL-…
Text-to-Audio-Video (T2AV) generation aims to produce temporally and semantically aligned visual and auditory content from natural language descriptions. While recent progress in text-to-audio and text-to-video models has improved generation quality within each modality, jointly modeling them remain…
Bitstream-corrupted video recovery aims to fill in realistic video content due to bitstream corruption during video storage or transmission. Most existing methods typically assume that the predefined masks of the corrupted regions are known in advance. However, manually annotating these masks is lab…
In-context learning (ICL) has revolutionized natural language processing by enabling models to adapt to diverse tasks with only a few illustrative examples. However, the exploration of ICL within the field of computer vision remains limited. Inspired by Chain-of-Thought (CoT) prompting in the langua…
Sound-guided object segmentation has drawn considerable attention for its potential to enhance multimodal perception. Previous methods primarily focus on developing advanced architectures to facilitate effective audio-visual interactions, without fully addressing the inherent challenges posed by aud…
Non-transferable learning (NTL) has been proposed to protect model intellectual property (IP) by creating a "non-transferable barrier" to restrict generalization from authorized to unauthorized domains. Recently, well-designed attack, which restores the unauthorized-domain performance by fine-tuning…
Accurately localizing audible objects based on audio-visual cues is the core objective of audio-visual segmentation. Most previous methods emphasize spatial or temporal multi-modal modeling, yet overlook challenges from ambiguous audio-visual correspondences--such as nearby visually similar but acou…
Existing audio-visual segmentation datasets typically focus on short-trimmed videos with only one pixel-map annotation for a per-second video clip. In contrast for untrimmed videos the sound duration start- and end-sounding time positions and visual deformation of audible objects vary significantly.…
Contrastive learning, while highly effective for a lot of tasks, shows limited improvement in ordinal regression. We find that the limitation comes from the predefined strong data augmentations employed in contrastive learning. Intuitively, for ordinal regression datasets, the discriminative inform…
Convolutional Neural Networks (CNNs) are powerful in learning patterns of different vision tasks, but they are sensitive to label noise and may overfit to noisy labels during training. The early stopping strategy averts updating CNNs during the early training phase and is widely employed in the pres…
In this paper, we empirically investigate a previously overlooked and widespread type of label noise, subclass-dominant label noise (SDN). Our findings reveal that, during the early stages of training, deep neural networks can rapidly memorize mislabeled examples in SDN. This phenomenon poses challe…
Filter pruning is essential for deploying a well-trained CNN model on edge computation devices with a target computation budget (e.g., FLOPs). Current filter pruning methods mainly focus on leveraging feature maps to analyze the importance of filters, and prune those with less impact on the value of…
Most recent self-supervised learning methods learn visual representation by contrasting different augmented views of images. Compared with supervised learning, more aggressive augmentations have been introduced to further improve the diversity of training pairs. However, aggressive augmentations may…