Video-based Generalized Category Discovery via Memory-Guided Consistency-Aware Contrastive Learning
By: Zhang Jing , Pu Nan , Xie Yu Xiang and more
Potential Business Impact:
Helps computers find new things in videos.
Generalized Category Discovery (GCD) is an emerging and challenging open-world problem that has garnered increasing attention in recent years. Most existing GCD methods focus on discovering categories in static images. However, relying solely on static visual content is often insufficient to reliably discover novel categories. To bridge this gap, we extend the GCD problem to the video domain and introduce a new setting, termed Video-GCD. Thus, effectively integrating multi-perspective information across time is crucial for accurate Video-GCD. To tackle this challenge, we propose a novel Memory-guided Consistency-aware Contrastive Learning (MCCL) framework, which explicitly captures temporal-spatial cues and incorporates them into contrastive learning through a consistency-guided voting mechanism. MCCL consists of two core components: Consistency-Aware Contrastive Learning(CACL) and Memory-Guided Representation Enhancement (MGRE). CACL exploits multiperspective temporal features to estimate consistency scores between unlabeled instances, which are then used to weight the contrastive loss accordingly. MGRE introduces a dual-level memory buffer that maintains both feature-level and logit-level representations, providing global context to enhance intra-class compactness and inter-class separability. This in turn refines the consistency estimation in CACL, forming a mutually reinforcing feedback loop between representation learning and consistency modeling. To facilitate a comprehensive evaluation, we construct a new and challenging Video-GCD benchmark, which includes action recognition and bird classification video datasets. Extensive experiments demonstrate that our method significantly outperforms competitive GCD approaches adapted from image-based settings, highlighting the importance of temporal information for discovering novel categories in videos. The code will be publicly available.
Similar Papers
Dissecting Generalized Category Discovery: Multiplex Consensus under Self-Deconstruction
CV and Pattern Recognition
Helps computers learn new things like humans do.
ClearGCD: Mitigating Shortcut Learning For Robust Generalized Category Discovery
CV and Pattern Recognition
Helps computers learn new things without forgetting old ones.
Learning Part Knowledge to Facilitate Category Understanding for Fine-Grained Generalized Category Discovery
CV and Pattern Recognition
Helps computers tell apart very similar things.