arXiv Computer Vision

Exploiting Stability-Plasticity Asymmetry in Pretrained Detectors for Incremental Object Detection

arXiv Machine Learning

Jun 5

Two-Way Is Better Than One: Bidirectional Alignment with Cycle Consistency for Exemplar-Free Class-Incremental Learning

arXiv:2606. 05675v1 Announce Type: new Abstract: Continual learning (CL) seeks models that acquire new skills without erasing prior knowledge.

By Hongye Xu, Bartosz Krawczyk

rag benchmarks safety

arXiv Computer Vision

Aug 25

C$^2$Path: Class-Conditional Pathway Decoupling for Vision-Language Incremental Object Detection

arXiv:2608.21937v1 Announce Type: new Abstract: Incremental Object Detection (IOD) aims to enable detectors to continuously learn novel categories while preserving previously acquired knowledge. Howe...

By Lecheng Xu, Feifei Shao, Ouyangzi Ye, Zhen Wang, Lin Li, Kexin Li, Zhao Wang, Changqin Huang

computer-vision multimodal benchmarks

arXiv AI

Jul 16

Symbiosis-Inspired Knowledge Distillation for Incremental Object Detection

arXiv:2607. 13452v1 Announce Type: cross Abstract: Incremental object detection (IOD) aims to extend detectors to new categories while retaining previously acquired knowledge.

By Mingyue Zeng, De Cheng, Zhipeng Xu, Huaijie Wang, Nannan Wang, Xinbo Gao

computer-vision efficiency safety

arXiv AI

Jul 29

Multi-Scale Structural Features for Continual, Comprehensible Visual Recognition in a Developmental Learning Framework

arXiv:2607. 25531v1 Announce Type: cross Abstract: Contemporary machine learning struggles to learn continually, reuse prior knowledge, and expose a comprehensible internal structure.

By Zeki Doruk Erden

benchmarks

arXiv Computer Vision

Sep 16

HyCal: A Training-Free Prototype Calibration Method for Cross-Discipline Few-Shot Class-Incremental Learning

arXiv:2604.15678v2 Announce Type: replace Abstract: Pretrained Vision-Language Models (VLMs) like CLIP show promise in continual learning, but existing Few-Shot Class-Incremental Learning (FSCIL) met...

By Eunju Lee, MiHyeon Kim, JuneHyoung Kwon, Yoonji Lee, JiHyun Kim, Soojin Jang, YoungBin Kim

llms rag multimodal benchmarks safety

arXiv AI

5d ago

Prompt-Based Continual Compositional Zero-Shot Learning

The paper introduces PromptCCZSL, a framework that enables vision‑language models to continually learn new attributes, objects, and their unique compositions while avoiding forgetting. It uses a frozen VLM backbone with prompt‑based techniques, recency‑weighted multi‑teacher distillation, and several loss functions (CAL, OPL, IDL) to maintain prior knowledge and promote diverse, distinct embeddings. Experiments on UT‑Zappos and C‑GQA show significant performance gains over existing VLM‑based and non‑VLM baselines, establishing a new benchmark for continual compositional zero‑shot learning.

By Sauda Maryam, Sara Nadeem, Faisal Qureshi, Mohsen Ali

llms rag efficiency multimodal benchmarks

arXiv Computer Vision

Sep 14

DRDN: Decoupled Representation Dynamic Network for From-Scratch ViT Class-Incremental Learning

arXiv:2607.01630v2 Announce Type: replace Abstract: Dynamic expansion methods for class-incremental learning (CIL) protect task-specific knowledge by growing dedicated tokens or subnetworks, yet our...

By Bingchen Huang, Yifu Chen, Zhiling Wang, Yuanchao Du

llms

arXiv AI

Jul 1

Real-Time Source-Free Object Detection

arXiv:2606. 31834v1 Announce Type: cross Abstract: Real-world detectors for autonomous driving, surveillance, and robotics must handle domain-shifts under strict latency and memory constraints, yet existing source-free object detection (SFOD) methods rely on heavyweight architectures that prioritize accuracy alone.

By Sairam VCR, Varun Gopal, Poornima Jain, Vineeth N Balasubramanian, Muhammad Haris Khan

agents computer-vision robotics efficiency benchmarks

arXiv Machine Learning

Sep 1

One Adapter, Many Tasks: Task-Conditioned Feature Transformations for Continual Learning

arXiv:2608.31096v1 Announce Type: cross Abstract: Class-incremental learning (CIL) requires a model to incrementally learn tasks that contain new classes without accessing earlier training data while...

By Yunxiang Fu, Meng Lou, Yizhou Yu

fine-tuning

arXiv Computer Vision

Aug 21

OrthoSkillVLA: Continual Skill Learning via Gradient-Informed Skill Subspace Adaptation

arXiv:2608. 19589v1 Announce Type: cross Abstract: Pretrained Vision-Language-Action models provide a strong foundation for robot learning, but sequentially adapting them to diverse skills can perturb the representations and velocity mappings used by previous skills, leading to catastrophic forgetting.

By Jiaqi Wang, Zhou Fang, Qiongfeng Shi, Yi Zhou

robotics multimodal

arXiv Computer Vision

Sep 18

Enhanced Knowledge Distillation for Detection Transformer via Teacher Prediction Refinement

The paper introduces Teacher Prediction Refinement Distillation (TPRD), a plug‑in module for Detection Transformers that refines teacher predictions before distillation. TPRD corrects degraded positive predictions and suppresses overconfident negatives, while preserving informative dark knowledge through Maximum Dark Knowledge Preservation. Experiments on MS COCO and PASCAL VOC show that these refinements improve the quality of supervision and the resulting student model’s performance.

By Yitong Xing, Yuhao Cheng, Yanping Li, Yichao Yan

llms computer-vision efficiency

arXiv Machine Learning

Jun 5

Revisiting Prototype Rehearsal for Exemplar-Free Continual Learning: Manifold-Aware Boundary Sampling with Adaptive Class-Balanced Loss

arXiv:2606. 05695v1 Announce Type: new Abstract: Exemplar-free class-incremental learning (EFCIL) aims to acquire new classes over time without storing raw data.

By Hongye Xu, Bartosz Krawczyk

benchmarks

Related stories