12 papers
Sustaining Plasticity via Learnable Wavelet Activations in Continual Learning
Zeyang Zhang, Tieliang Gong, Junyan Lu +1
Plasticity loss has emerged as a critical challenge in continual learning that significantly hinders the acquisition of sequential tasks. While optimizing activation designs offers…
Drift and Dependence: Layer-wise Information-Theoretic Bounds for Replay-Based Continual Learning
Tieliang Gong, Zhongbo Zhang, Wen Wen +1
Continual learning must absorb new tasks without erasing old ones, and replay---mixing a small buffer of past examples into current training---is among the most effective remedies…
Beyond Sharpness: A Flatness Decomposition Framework for Efficient Continual Learning
Yanan Chen, Tieliang Gong, Yunjiao Zhang +1
Continual Learning (CL) aims to enable models to sequentially learn multiple tasks without forgetting previous knowledge. Recent studies have shown that optimizing towards flatter…
Information-Theoretic Generalization Bounds of Replay-based Continual Learning
Wen Wen, Tieliang Gong, Zeyu Gao +3
Continual learning (CL) has emerged as a dominant paradigm for acquiring knowledge from sequential tasks while avoiding catastrophic forgetting. Although many CL methods have been…
Unsupervised Structural Scene Decomposition via Foreground-Aware Slot Attention with Pseudo-Mask Guidance
Huankun Sheng, Ming Li, Yixiang Wei +4
Recent advances in object-centric representation learning have shown that slot attention-based methods can effectively decompose visual scenes into object slot representations with…
Rectified Diffusion Guidance for Conditional Generation
Mengfei Xia, Nan Xue, Yujun Shen +3
Classifier-Free Guidance (CFG), which combines the conditional and unconditional score functions with two coefficients summing to one, serves as a practical technique for diffusion…