# Image Classification on CIFAR-100 (W4A4 and W3A3 Performance)

Source: [Image Classification on CIFAR-100 (W4A4 and W3A3 Performance)](<https://www.sota2.com/research/sota/image-classification-on-cifar-100-w4a4-and-w3a3-performance>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2026-02-26T06:08:21.450Z

Evaluation of Image Classification performance on the CIFAR-100 dataset, focusing on metrics related to model performance under specific weight and activation quantization schemes (W4A4 and W3A3).

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

| Scope | Recorded value |
| --- | --- |
| Task | Image Classification |
| Dataset (including any stated split) | CIFAR-100 |
| Metric | W4A4 Error |
| Unit | PERCENT |
| Direction | Lower is better |
| Results loaded | 4 of 4 |
| Coverage | All results currently returned for this benchmark |

Evaluation settings may differ between results. The original papers and recorded configurations are needed to establish comparability. A shared metric name alone does not establish an identical protocol.

## Metrics

- [W4A4 Error](<https://www.sota2.com/research/sota/image-classification-on-cifar-100-w4a4-and-w3a3-performance.md?metric=W4A4%20Error>): Lower is better; unit: PERCENT.

- [W3A3 Error](<https://www.sota2.com/research/sota/image-classification-on-cifar-100-w4a4-and-w3a3-performance.md?metric=W3A3%20Error>): Lower is better; unit: PERCENT.

## Recorded results

| Method | W4A4 Error | Result date | Report paper |
| --- | --- | --- | --- |
| CNN AdaRound | -2.01 | Not recorded | 68fa6e3b1e209131cea3e7fb |
| AddNN | -1.83 | Not recorded | 68fa6e3b1e209131cea3e7fb |
| CNN BRECQ | -1.74 | Not recorded | 68fa6e3b1e209131cea3e7fb |
| CNN QDROP | -1.7 | Not recorded | 68fa6e3b1e209131cea3e7fb |

### CNN AdaRound

W4A4 Error: -2.01. Result ID: 6990093e3a6c314849fda545.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6e3b1e209131cea3e7fb.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa67d61e209131cea18d09.md>)

Recorded evaluation configuration: {"Architecture":"CNN"}. This record does not assert independent reproduction.

### AddNN

W4A4 Error: -1.83. Result ID: 6990093e3a6c314849fda544.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6e3b1e209131cea3e7fb.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6e3b1e209131cea3e7fb.md>)

[Implementation](<https://gitee.com/mindspore/models/tree/master/research/cv/AdderQuant>)

Recorded evaluation configuration: {"Architecture":"AdderNet"}. This record does not assert independent reproduction.

### CNN BRECQ

W4A4 Error: -1.74. Result ID: 6990093e3a6c314849fda546.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6e3b1e209131cea3e7fb.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6a751e209131cea2842c.md>)

Recorded evaluation configuration: {"Architecture":"CNN"}. This record does not assert independent reproduction.

### CNN QDROP

W4A4 Error: -1.7. Result ID: 6990093e3a6c314849fda547.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6e3b1e209131cea3e7fb.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6e981e209131cea40f7a.md>)

Recorded evaluation configuration: {"Architecture":"CNN"}. This record does not assert independent reproduction.

Page 1 of 1. This is an index page, not the full collection.
