Pith. sign in

REVIEW 12 cited by

Noise or Signal: The Role of Image Backgrounds in Object Recognition

Not yet reviewed by Pith; the record is open.

Re-run · record.json Download PDF Read on arXiv ↗

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2006.09994 v1 pith:EO2XZNOI submitted 2020-06-17 cs.CV cs.LG

Kai Xiao , Logan Engstrom , Andrew Ilyas , Aleksander Madry This is my paper
classification cs.CVcs.LG
keywords modelsbackgroundsbackgrounddependimageimagesobjectrecognition
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

We assess the tendency of state-of-the-art object recognition models to depend on signals from image backgrounds. We create a toolkit for disentangling foreground and background signal on ImageNet images, and find that (a) models can achieve non-trivial accuracy by relying on the background alone, (b) models often misclassify images even in the presence of correctly classified foregrounds--up to 87.5% of the time with adversarially chosen backgrounds, and (c) more accurate models tend to depend on backgrounds less. Our analysis of backgrounds brings us closer to understanding which correlations machine learning models use, and how they determine models' out of distribution performance.

Discussion (0). Sign in to comment.

Forward citations

Cited by 12 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. Detectors Learn the Wrong Thing: Shortcut-Resistant Adversarial Training Against Physically Realizable Attacks

    cs.CV 2026-07 conditional novelty 7.0 of 10

    InsCAT adds a contrastive loss that aligns adversarially clothed people with clean people and pushes away from texture-only images, reducing texture false positives from 46.9% to 7.3% while lifting average attack AP to 82.3%.

  2. LeVLJEPA: End-to-End Vision-Language Pretraining Without Negatives

    cs.CV 2026-07 unverdicted novelty 7.0 of 10

    LeVLJEPA is the first non-contrastive vision-language pretraining method that learns via cross-modal prediction without negatives, producing stronger dense features than contrastive baselines on VQA and segmentation tasks.

  3. From Measurement to Mitigation: Quantifying and Reducing Identity Leakage in Image Representation Encoders with Linear Subspace Removal

    cs.CV 2026-04 conditional novelty 7.0 of 10

    Visual encoders leak identity information; a one-shot linear subspace removal method (ISP) reduces leakage to near-chance levels while retaining high non-biometric utility across datasets.

  4. Spurious Correlation Learning in Preference Optimization: Mechanisms, Consequences, and Mitigation via Tie Training

    cs.LG 2026-05 unverdicted novelty 6.0 of 10

    Standard preference learning induces spurious feature reliance via mean bias and correlation leakage, creating irreducible distribution shift vulnerabilities that tie training mitigates without degrading causal learning.

  5. Spurious Correlation Learning in Preference Optimization: Mechanisms, Consequences, and Mitigation via Tie Training

    cs.LG 2026-05 unverdicted novelty 6.0 of 10

    Characterizes spurious correlation mechanisms in preference optimization via mean spurious bias and causal-spurious correlation leakage, demonstrates irreducible vulnerability to distribution shift, and introduces tie...

  6. R3G: A Reasoning-Retrieval-Reranking Framework for Vision-Centric Answer Generation

    cs.CV 2026-01 unverdicted novelty 6.0 of 10

    R3G improves vision-centric visual question answering by generating reasoning plans to guide two-stage image retrieval and reranking, achieving state-of-the-art results on MRAG-Bench across six MLLM backbones.

  7. AIM: Amending Inherent Interpretability via Self-Supervised Masking

    cs.CV 2025-08 unverdicted novelty 6.0 of 10

    AIM uses multi-stage feature guidance for self-supervised masking to improve both interpretability (EPG) and accuracy on vision benchmarks.

  8. Shortcut Learning in Generalist Robot Policies: The Role of Dataset Diversity and Fragmentation

    cs.RO 2025-08 conditional novelty 6.0 of 10

    Low within-subdataset diversity and large between-subdataset differences cause shortcut learning in generalist robot policies, and targeted augmentation can mitigate it.

  9. R3G: A Reasoning-Retrieval-Reranking Framework for Vision-Centric Answer Generation

    cs.CV 2026-01 conditional novelty 5.0 of 10

    R3G improves vision-centric VQA by generating a reasoning plan before retrieval and reranking candidate images with an MLLM judge on relevance, target match, and answerability.

  10. SPARSE Data, Rich Results: Few-Shot Semi-Supervised Learning via Class-Conditioned Image Translation

    cs.CV 2025-08 unverdicted novelty 5.0 of 10

    A GAN framework that translates unlabeled medical images between classes and fuses ensemble, time-averaged pseudo-labels outperforms six prior GAN semi-supervised methods on MedMNIST at 5-50 labels per class.

  11. Common Inpainted Objects In-N-Out of Context

    cs.CV 2025-05 unverdicted novelty 5.0 of 10

    COinCO is a new dataset of inpainted COCO images with in- and out-of-context objects, enabling context reasoning, object prediction from scenes, and improved fake image detection.

  12. Training-Free Object-Background Compositional T2I via Dynamic Spatial Guidance and Multi-Path Pruning

    cs.CV 2026-04 unverdicted novelty 4.0 of 10

    A training-free method with time-dependent attention gating and trajectory pruning enhances object-background balance in diffusion-based image synthesis.

Pith tools