Methods › General › Interpretability › Network Dissection
Network Dissection
Introduced by Bolei Zhou et al. in Interpreting Deep Visual Representations via Network Dissection
archive 2025-07-28 Description, source and code snippet are the archive's method entry.
Network Dissection is an interpretability method for CNNs that evaluates the alignment between individual hidden units and a set of visual semantic concepts. By identifying the best alignments, units are given human interpretable labels across a range of objects, parts, scenes, textures, materials, and colors.
The measurement of interpretability proceeds in three steps:
- Identify a broad set of human-labeled visual concepts.
- Gather the response of the hidden variables to known concepts.
- Quantify alignment of hidden variable−concept pairs.
In Syntology about another paper, arXiv:1704.05796: repository known, no verified implementation (declared_code; repositories: 1 listed of 1 in the graph, strongest link: official). The lookup matched a paper by its title, arXiv:1704.05796, not a method entry. About another paper: this answer is about arXiv:1704.05796, while the archive credits arXiv:1711.05611.
Origin paper of this answer, arXiv:1704.05796 (its page on this site · its page on Syntology).
Syntology's have check for this name (free, it answers coverage only), read 2026-10-05; ask it again live. A level is the served verification level of that one answer; nothing here is summed across methods.
Papers archive 2025-07-28
archive papers tagged: 11 · with a code link: 8 · where Syntology ran a sample: 3 (2 with a run with no instrument failure, 1 where every run was a failure of Syntology's instrument) Syntology
Show: all tagged papersonly where code ran (3 of 11 tagged: 2 with a run with no instrument failure, 1 where every run was a failure of Syntology's instrument)
Page 1 of 1: papers 1 to 11 of 11, newest first by the archive's date (ties by slug), in archive order.
Repository counts are the archive's code-links table. A Syntology line states what Syntology ran from that paper's harvested code, as “N ran (of which C constructed an object rather than computing a result; K with no instrument failure: H honoured, V violated, P with no contract checked; I where Syntology's instrument failed) · U unverified”; the instrument figure counts failures of Syntology's instrument, not of the code. It is per sample and not a correctness claim. When the archive marks a repository official for the paper, the line starts with that repository's state (the archive's flag, not a verdict on who wrote the code; “community repositories only” when every sample that ran came from a community repository, “official: no sample here; runs from other or unrecorded repositories” when some came from a repository the paper names or has in its text, or from none recorded); hover it for the repositories the samples that ran came from.
-
Labeling Neural Representations with Inverse Recognition 22 Nov 2023 · 2 repositories · arXiv:2311.13594Syntology official (archive's flag): 4 ran · 4 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified (of 4 harvested samples) · 4 pointer-only (licence)
-
DISCOVER: Making Vision Networks Interpretable via Competition and Dissection 21 Sep 2023 · 1 repository
-
On the Impact of Knowledge Distillation for Model Interpretability 25 May 2023 · 0 repositories · arXiv:2305.15734
-
Detection Accuracy for Evaluating Compositional Explanations of Units 16 Sep 2021 · 1 repository · arXiv:2109.07804
-
Interpreting Face Inference Models using Hierarchical Network Dissection 23 Aug 2021 · 1 repository · arXiv:2108.10360
-
Gated Convolutional Networks with Hybrid Connectivity for Image Classification 26 Aug 2019 · 1 repository · arXiv:1908.09699Syntology official (archive's flag): 3 ran · 4 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 4 where Syntology's instrument failed) · 1 unverified (of 5 harvested samples) · 5 pointer-only (licence)
-
Interpreting Adversarial Examples by Activation Promotion and Suppression 3 Apr 2019 · 0 repositories · arXiv:1904.02057
-
On the Units of GANs (Extended Abstract) 29 Jan 2019 · 0 repositories · arXiv:1901.09887
-
GAN Dissection: Visualizing and Understanding Generative Adversarial Networks 26 Nov 2018 · 8 repositories · arXiv:1811.10597Syntology official (archive's flag): 10 ran · 25 ran (of which 0 constructed an object rather than computing a result; 23 with no instrument failure: 0 honoured, 0 violated, 23 with no contract checked; 2 where Syntology's instrument failed) · 9 unverified (of 34 harvested samples) · 3 pointer-only (licence)
-
How convolutional neural network see the world - A survey of convolutional neural network visualization methods 30 Apr 2018 · 1 repository · arXiv:1804.11191
-
Interpreting Deep Visual Representations via Network Dissection 15 Nov 2017 · 3 repositories · arXiv:1711.05611
Tasks archive 2025-07-28
16 tasks the archive attaches to papers tagged with this method, by distinct papers. A task without a page in the catalog is plain text.
Usage over time archive 2025-07-28
Components: the archive holds no method-to-method composition, so PwC's Components table cannot be rebuilt; the Papers list carries no Results column for the same reason (the archive does not join its leaderboard rows to method tags).
Categories archive 2025-07-28
Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections