Beyond the Pixels: Exploring the Effects of Bit-Level Network and File Corruptions on Video Model Robustness
We investigate the robustness of video machine learning models to bit-level network and file corruptions, which can arise from network transmission failures or hardware errors, and explore defenses against such corruptions. We simulate network and file corruptions at multiple corruption levels, and find that bit-level corruptions can cause substantial performance drops on common action recognition and multi-object tracking tasks. We explore two types of defenses against bit-level corruptions: corruption-agnostic and corruption-aware defenses. We find that corruption-agnostic defenses such as adversarial training have limited effectiveness, performing up to 11.3 accuracy points worse than a no-defense baseline. In response, we propose Bit-corruption Augmented Training (BAT), a corruption-aware baseline that exploits knowledge of bit-level corruptions to enforce model invariance to such corruptions. BAT outperforms corruption-agnostic defenses, recovering up to 7.1 accuracy points over a no-defense baseline on highly-corrupted videos while maintaining competitive performance on clean/near-clean data.
Code (0)
등록된 구현이 없습니다.
Tasks
Action RecognitionMulti-Object TrackingObject TrackingSimilar Papers 제목 키워드 기반
Disentangled Latent Transformer for Interpretable Monocular Height Estimation
Monocular height estimation (MHE) from remote sensing imagery has high potential in generating 3D city models efficiently for a quick response to natural disasters. Most existing works pursue higher performance. However,…
Semantic SegmentationUnsupervised Semantic SegmentationFrom Pixels to Buildings: End-to-end Probabilistic Deep Networks for Large-scale Semantic Mapping
We introduce TopoNets, end-to-end probabilistic deep networks for modeling semantic maps with structure reflecting the topology of large-scale environments. TopoNets build a unified deep network spanning multiple levels …
Rule of Three for Superresolution of Still Images with Applications to Compression and Denoising
We describe a new method for superresolution of still images (in the wavelet domain) based on the reconstruction of missing details subbands pixels at a given ith level via Rule of Three (Ro3) between pixels of approxima…
DenoisingLoc2Repair: A Framework for Evaluating the Impact of File-Level Issue Localization in Repo-Level LLM Repair
Repository-grounded automated repair is often reported as a single end-to-end capability, which hides distinct failure modes such as poor file targeting, incorrect patch synthesis, and failed iterative debugging. We pres…
Scaling Law in LLM Simulated Personality: More Detailed and Realistic Persona Profile Is All You Need
This research focuses on using large language models (LLMs) to simulate social experiments, exploring their ability to emulate human personality in virtual persona role-playing. The research develops an end-to-end evalua…